644 Chapter 19 Probability and Statistics in Engineering
students, then we might be able to use the probability distribution for this class to predict how
students might do on a similar test next year. Often, it is difficult to define what we mean by
a typical class or a typical test. However, if we had a lot more students take this test and incor-
porate their scores into our analysis, we might be able to use the results of this experiment to
predict the outcomes of a similar test to be given later. As the number of students taking the
test increases (leading to more scores), the line connecting the midpoint of scores shown in
Figure 19.4 becomes smoother and approaches a bell-shaped curve. We use the next example
to further explain this concept.
Example 19.4 In order to improve the production time, the supervisor of assembly lines in a manufacturing
setting of computers has studied the time that it takes to assemble certain parts of a computer
at various stations. She measures the time that it takes to assemble a specific part by 100 people
at different shifts and on different days. The record of her study is organized and shown in
Table 19.10.
TABLE 19.10 Data Pertaining to Example 19.4
Time That It
Takes a Person
to Assemble the
Part (minutes) Frequency Probability
5 5 0.05
6 8 0.08
7 11 0.11
8 15 0.15
9 17 0.17
10 14 0.14
11 13 0.13
12 8 0.08
13 6 0.06
14 3 0.03
Based on data provided, we have calculated the probabilities corresponding to the time
intervals that people took to assemble the parts. The probability distribution for
Example 19.4 is shown in Table 19.10 and Figure 19.5. Again, note that the sum of proba-
bilities is equal to 1. Also note that if we were to connect the midpoints of time results
(as shown in Figure 19.5), we would have a curve that approximates a bell shape. As the
number of data points increases and the intervals decrease, the probability-distribution curve
becomes smoother. A probability distribution that has a bell-shaped curve is called anormal
distribution. The probability distribution for many engineering experiments is approximated
by a normal distribution.
Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
圀圀圀⸀夀䄀娀䐀䄀一倀刀䔀匀匀⸀䌀伀䴀圀圀圀⸀夀䄀娀䐀䄀一倀刀䔀匀匀⸀䌀伀䴀